Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0508. Min Range: -7.0508
Max Act: 7.0508. Min Act: -0.1700
Data Index: 7979888 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.7383. Min Act: -0.1700
Data Index: 4723098 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.6758. Min Act: -0.1700
Data Index: 7834720 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.6445. Min Act: -0.1700
Data Index: 1521760 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.6133. Min Act: -0.1700
Data Index: 766828 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.5508. Min Act: -0.1700
Data Index: 3124083 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.5195. Min Act: -0.1700
Data Index: 1454934 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.5195. Min Act: -0.1700
Data Index: 6886518 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.5195. Min Act: -0.1700
Data Index: 8796552 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.5195. Min Act: -0.1700
Data Index: 8808903 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.4883. Min Act: -0.1700
Data Index: 3858868 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.4883. Min Act: -0.1700
Data Index: 5942188 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.4883. Min Act: -0.1700
Data Index: 202960 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.4570. Min Act: -0.1700
Data Index: 3891047 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.5195. Min Act: -0.1700
Data Index: 4285686 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.4570. Min Act: -0.1700
Data Index: 8037356 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.4258. Min Act: -0.1700
Data Index: 5588686 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.3945. Min Act: -0.1700
Data Index: 6455696 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.3320. Min Act: -0.1700
Data Index: 8046988 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0508. Min Range: -7.0508
Max Act: 6.3320. Min Act: -0.1700
Data Index: 6730685 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19